Method Details
Details for method 'PolyTransform + SegFix'
Method overview
| name | PolyTransform + SegFix |
| challenge | instance-level semantic labeling |
| details | We simply apply a novel post-processing scheme based on the PolyTransform (thanks to the authors of PolyTransform for providing their segmentation results). The performance of the baseline PolyTransform is 40.1% and our method achieves 41.2%. Besides, our method also could improve the results of PointRend and PANet by more than 1.0% without any re-training or fine-tuning the segmentation models. |
| publication | Anonymous openseg |
| project page / code | https://github.com/openseg-group/openseg.pytorch |
| used Cityscapes data | fine annotations |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | no |
| submission date | March, 2020 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| AP | 41.2362 |
| AP50% | 66.0805 |
| AP100m | 56.02 |
| AP50m | 59.2404 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 44.3015 | 76.2095 | 61.8479 | 61.9451 |
| rider | 35.9096 | 72.0527 | 50.4264 | 51.047 |
| car | 60.5257 | 82.7781 | 79.2401 | 81.7918 |
| truck | 40.4956 | 52.4348 | 54.7834 | 63.4857 |
| bus | 51.2162 | 68.6952 | 69.2896 | 76.4225 |
| train | 41.559 | 63.3475 | 57.5299 | 63.4533 |
| motorcycle | 31.7363 | 58.8339 | 40.7866 | 41.5277 |
| bicycle | 24.1456 | 54.2924 | 34.2558 | 34.25 |